Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[Breaking] Require format to be specified in input URI. (#9077)

Browse Source 
Previously, we use `libsvm` as default when format is not specified. However, the dmlc
data parser is not particularly robust against errors, and the most common type of error
is undefined format.

Along with which, we will recommend users to use other data loader instead. We will
continue the maintenance of the parsers as it's currently used for many internal tests
including federated learning.
This commit is contained in:
Jiaming Yuan
2023-04-28 19:45:15 +08:00
committed by GitHub
parent e922004329
commit 1f9a57d17b
58 changed files with 327 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/cpp/data/test_simple_dmatrix.cc
View File

@@ -17,11 +17,15 @@
using namespace xgboost; // NOLINT
namespace {
std::string UriSVM(std::string name) { return name + "?format=libsvm"; }
} // namespace
TEST(SimpleDMatrix, MetaInfo) {
dmlc::TemporaryDirectory tempdir;
const std::string tmp_file = tempdir.path + "/simple.libsvm";
CreateSimpleTestData(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(UriSVM(tmp_file));
// Test the metadata that was parsed
EXPECT_EQ(dmat->Info().num_row_, 2);
@@ -37,7 +41,7 @@ TEST(SimpleDMatrix, RowAccess) {
dmlc::TemporaryDirectory tempdir;
const std::string tmp_file = tempdir.path + "/simple.libsvm";
CreateSimpleTestData(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(tmp_file, false);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(UriSVM(tmp_file), false);
// Loop over the batches and count the records
int64_t row_count = 0;
@@ -60,7 +64,7 @@ TEST(SimpleDMatrix, ColAccessWithoutBatches) {
dmlc::TemporaryDirectory tempdir;
const std::string tmp_file = tempdir.path + "/simple.libsvm";
CreateSimpleTestData(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(tmp_file);
xgboost::DMatrix *dmat = xgboost::DMatrix::Load(UriSVM(tmp_file));
ASSERT_TRUE(dmat->SingleColBlock());
@@ -387,7 +391,7 @@ TEST(SimpleDMatrix, SaveLoadBinary) {
dmlc::TemporaryDirectory tempdir;
const std::string tmp_file = tempdir.path + "/simple.libsvm";
CreateSimpleTestData(tmp_file);
xgboost::DMatrix * dmat = xgboost::DMatrix::Load(tmp_file);
xgboost::DMatrix * dmat = xgboost::DMatrix::Load(UriSVM(tmp_file));
data::SimpleDMatrix *simple_dmat = dynamic_cast<data::SimpleDMatrix*>(dmat);
const std::string tmp_binfile = tempdir.path + "/csr_source.binary";